In this paper, we explain why we have adopted pattern matching for MT purposes and why we have embedded it into a hybrid approach. 'Patterns' here are understood as independent meaningful sub-sentential segments received in a systematic way. We describe the nature and size of the patterns used as well as the comparison algorithm developed. We discuss results obtained by matching patterns of different types and complexity in four different language pairs. Our experiments indicate that better results are obtained when matching the longest possible patterns.