Requirements are usually “hand-written” and suffers from several problems like redundancy and inconsistency. The problems of redundancy and inconsistency between requirements or sets of requirements impact negatively the success of final products. Manually processing these issues requires too much time and it is very costly. The main contribution of this paper is the use of k-means algorithm for a redundancy and inconsistency detection in a new context, which is Requirements Engineering context. Also, we introduce a pre-processing step based on the Natural Language Processing (NLP) techniques to see the impact of this latter to the k-means results. We use Part-Of-Speech (POS) tagging and noun chunking to detect technical busi-ness terms associated to the requirements documents that we analyze. We experiment this approach on real industrial datasets. The results show the efficiency of the k-means clustering algorithm especially with the pre-processing.