In Community Question Answering (CQA) systems, when a user makes a question query, a set of questions similar to the new one, and that have already been answered by other users, are automatically retrieved from the questions archive. The quality and efficiency of these systems mainly lie on their ability to find the most appropriate answer(s) to a certain question. Various textual similarity approaches are used in the question answering process. We focus on semantic similarity approaches since they are found to be more suitable than statistical and bag-of-words measures for short and natural language texts, which is the case in CQA systems. The aim of this paper is to propose an effective and generic similarity approach for question answering systems. For knowledge reuse purpose, we adopt the Case-Based Reasoning (CBR), a powerful automatic reasoning process allowing to solve new problems based on solutions of similar past problems. The main step of the CBR process is the retrieval of similar cases, for which we perform a similarity calculation between the new question's text and the old ones' texts in order to retrieve the most similar questions, and identify the most useful content for answering a new problem. We propose a semantic Bayesian inference approach to address the semantic uncertainty implied by texts in natural language. Experiments conducted on our CQA system have shown promising results, and proved the efficiency of the proposed algorithms.