I am new to Mapreduce and I am using Hadoop Pipes for that. I have an input file which contains the number of records, one per line. I have written one simple program to print those lines in which three words are common. In map function i have emiited the word as a key and record as a value and compared those records in reduce function. I compared Hadoop's performance with simple C++ program in which I read the records from file and split it into words and load the data, word as a key and record as a value in map and after loading all the data I compared that data. But I found that for doing the same task Hadoop MapReduce takes long time compared with plain C++ program.