Semantic similarity measure technology based approach is one of the most popular approaches aiming at implementing semantic mapping between two different CAD model data ontologies. The most important problem in this approach is how to measure the semantic similarities of concepts between two different ontologies. A number of measure methods focusing on this problem have been presented in recent years. Each method can work well between its specific ontologies. But it is unclear how accurate the measured semantic similarities in these methods are. Moreover, there is yet no evidence that any of the methods presented how to select a measure with high similarity calculation accuracy. To compensate for such deficiencies, this paper proposes a method for selecting a semantic similarity measure with high similarity calculation accuracy for concepts in two different CAD model data ontologies. In this method, the similarity calculation accuracy of each candidate measure is quantified using Pearson correlation coefficient or residual sum of squares. The measure with high similarity calculation accuracy is selected through a comparison of the Pearson correlation coefficients or the residual sums of squares of all candidate measures. The paper also reports an implementation of the proposed method, provides an example to show how the method works, and evaluates the method by theoretical and experimental comparisons. The evaluation result suggests that the measure selected by the proposed method has good human correlation and high similarity calculation accuracy.