In automatic software bug localization, source code classes and methods are commonly used as the unit of suggestions. However, existing techniques consider whole source code to find the buggy locations, which degrades the accuracy of bug localization. In this paper, a Method level Bug localization using Minimized code space (MBuM) has been proposed which improves the accuracy by only considering bug specific source code. Later, this source code is used for identifying the similarity to the bug report. These similarity scores are measured using a modified Vector Space Model (mVSM), and based on that scores MBuM ranks a list of source code methods. The validity of MBuM has been checked by providing theoretical proof using formal methods. Case studies have been performed on two large scale open source projects namely Eclipse and Mozilla, and the results show that MBuM outperforms existing bug localization techniques.