The purpose of this review was to evaluate whether cone-beam computed tomography (CBCT) is reliable for the detection of bone changes of the temporomandibular joint (TMJ). Studies collected from the PubMed, Web of Science, Cochrane Library, ScienceDirect, Embase, Wanfang and CNKI databases were searched, and the publishing time was limited from January 1990 to December 2015. Eight studies (23 experimental research groups) were eventually included for further analysis. The pooled sensitivity was 0.67 and the pooled specificity was 0.87, which leads to a relatively large area (0.84) under the Receiver Operating Characteristic (ROC) curve. The related pooled positive likelihood ratio (+LR) and the pooled negative likelihood ratio (-LR) were 5.2 and 0.38, respectively. The subgroup analysis was conducted for four subgroups categorized by voxel size (≤0.2; >0.2, ≤0.3; >0.3, ≤0.4; >0.4, and ≤0.5 (mm)), and the ">0.4, ≤0.5" subgroup had a higher pooled sensitivity and pooled specificity than the other groups. The present study demonstrates that CBCT has a relatively high diagnostic accuracy for TMJ bone changes, although its reliability is limited. Voxel size did not play a role in the accuracy of CBCT.