Try this out - simple case of just getting a rough confidence interval for Dxy.
require(rms)
B <- 250; reps <- 500; dxy <- numeric(reps)
n <- nrow(d)
f <- lrm(y ~ x1 + x2 + x3 + ..., data=d, x=TRUE, y=TRUE)
f # show original model fit
validate(f, B=B) # show overall validation
for(i in 1 : reps) {
g <- update(f, subset=sample(1 : n, n, replace=TRUE))
v <- validate(g, B=B)
dxy[i] <- v['Dxy', 'index.corrected']
}
quantile(dxy, c(.025, .975))