[R] Linear models over large datasets

I'd like to fit linear models on very large datasets. My data frames are about 200 rows x 200 columns of doubles and I am using an 64 bit build of R. I've googled about this extensively and went over the R Data Import/Export guide. My primary issue is although my data represented in ascii form

[R] Data frame operations getting slower when accessed by index

I have a data frame called df which has about 100 columns but thousands of rows. I set D the index of df$D and M to be the index of df$M. When I run the following loop as it is vs. df[,D] and df[,M] replaced with df$D and df$M there is a real big time difference in completion (with the latter