Opportunistic screening using existing CT images may be a new strategy to identify subjects at increased risk for osteoporotic fracture. Low bone mineral density (BMD) is a key parameter but routine clinical CT scans do not include a calibration phantom to calculate BMD from the measured CT values. An alternative is internal or phantomless calibration, which is based on the CT values of air and of internal tissues of the subject such as blood, muscle or adipose tissue. However, the composition and as a consequence the CT values of these so-called internal calibration materials vary among subjects, which introduces additional BMD accuracy errors compared to phantom based calibration. The objective of this study was to quantify these accuracy errors and to identify optimum combinations of internal calibration materials (IM) for BMD assessments in opportunistic screening. Based on the base material decomposition theory we demonstrate how BMD can be derived from the CT values of the internal calibration materials. 121 CT datasets of the lumbar spine form postmenopausal women were used to determine the population variance of blood assessed in the aorta or the inferior vena cava, skeletal muscle of the erector spinae or psoas, subcutaneous adipose tissue (SAT) and air. The corresponding standard deviations were used for error propagation to determine phantomless calibration related BMD accuracy errors. Using a CT value of 150 HU, a typical value of trabecular bone, simulated BMD accuracy errors for most IM combinations containing air as one of the two base materials were below 5% or 6 mg/cm. The lowest errors were determined for the combination of blood and air (<2 mg/cm). The combination of blood and skeletal muscle resulted in higher errors (>10.5% or >12 mg/cm) and is not recommended. Due to possible age-related differences in tissue composition, the selection of IMs is suggested to be adapted according to the measured subject. In younger subjects without significant aortic calcifications, air and blood of the aorta may be the best combination whereas in elderly subjects, air and SAT (error of 4%) may be preferable. The use of skeletal muscle as one of the two IMs is discouraged, in particular in elderly subjects because of varying fatty infiltration. A practical implementation of the internal calibration with different IM pairs confirmed the theoretical results. In summary, compared to a phantom based calibration the phantomless approach used for opportunistic screening creates additional BMD accuracy errors of 2% or more, dependent on the used internal reference tissues. The impact on fracture prediction still must be evaluated.